Self-Adjustable Hybrid Metaheuristic Framework for Task Scheduling in Cloud Computing

Cloud computing through whose existence makes the computer industry revolutionized, provides the way to perform calculations at a small cost, with the availability of resources and flexibility. Task scheduling remains an attempt to maximize the performance of measures like make-span, energy usage, and cost, even though the user's tasks and the resources may be dynamic. The problems can be managed with hybrid metaheuristic algorithms, the benefits of which are seen in using different optimization approaches. This is a new type of research: The paper on Self-Adjustable Hybrid Metaheuristic (SAHM) framework, which is led by the various metaheuristic approaches like GA, PSO, SA, and MFO. The paper has with pro-active elements for smart strategy choice/card by means of the incorporation of past accomplishments on the fly. SAHM has an advantage over others in terms of energy and make-span since it utilizes the individual strengths of metaheuristics and at the same time it is considerably cheaper than others. The proposed framework has the possibility of running parallel executions, which makes it a proper choice for large-sized applications. A preliminary evaluation suggests that SAHM offers efficient framework of scheduling tasks in the dynamic cloud environments, and it outperforms single metaheuristics.